Multi-Agent-Deep-Deterministic-Policy-Gradients
Multi-Agent-Deep-Deterministic-Policy-Gradients copied to clipboard
I just fixed the problem about backward
here is the solution https://github.com/philtabor/Multi-Agent-Deep-Deterministic-Policy-Gradients/issues/2#issuecomment-912548033
The code of @Vishwanath1999 seems worked!Thank you, buddy!
But the different between old actions and actions from mu_states is still not clear to me. Maybe I need more studying.